Timezone: »
Methods to find counterfactual explanations have predominantly focused on one-step decision making processes. In this work, we initiate the development of methods to find counterfactual explanations for decision making processes in which multiple, dependent actions are taken sequentially over time. We start by formally characterizing a sequence of actions and states using finite horizon Markov decision processes and the Gumbel-Max structural causal model. Building upon this characterization, we formally state the problem of finding counterfactual explanations for sequential decision making processes. In our problem formulation, the counterfactual explanation specifies an alternative sequence of actions differing in at most k actions from the observed sequence that could have led the observed process realization to a better outcome. Then, we introduce a polynomial time algorithm based on dynamic programming to build a counterfactual policy that is guaranteed to always provide the optimal counterfactual explanation on every possible realization of the counterfactual environment dynamics. We validate our algorithm using both synthetic and real data from cognitive behavioral therapy and show that the counterfactual explanations our algorithm finds can provide valuable insights to enhance sequential decision making under uncertainty.
Author Information
Stratis Tsirtsis (Max Planck Institute for Software Systems)
Abir De (IIT Bombay)
Manuel Rodriguez (Max Planck Institute for Software Systems)
More from the Same Authors
-
2021 : Reinforcement Learning Under Algorithmic Triage »
Eleni Straitouri · Adish Singla · Vahid Balazadeh Meresht · Manuel Rodriguez -
2022 Poster: Counterfactual Temporal Point Processes »
Kimia Noorbakhsh · Manuel Rodriguez -
2023 Poster: Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search »
Indradyumna Roy · Rishi Agarwal · Soumen Chakrabarti · Anirban Dasgupta · Abir De -
2023 Poster: Learning to Select a Subset of Training Examples to Generalize Efficient Model Training »
Eeshaan Jain · Tushar Nandy · Gaurav Aggarwal · Ashish Tendulkar · Rishabh Iyer · Abir De -
2023 Poster: Finding Counterfactually Optimal Action Sequences in Continuous State Spaces »
Stratis Tsirtsis · Manuel Rodriguez -
2023 Poster: Human-Aligned Calibration for AI-Assisted Decision Making »
Nina Corvelo Benz · Manuel Rodriguez -
2022 Spotlight: Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection »
Abir De · Soumen Chakrabarti -
2022 Spotlight: Lightning Talks 1A-3 »
Kimia Noorbakhsh · Ronan Perry · Qi Lyu · Jiawei Jiang · Christian Toth · Olivier Jeunen · Xin Liu · Yuan Cheng · Lei Li · Manuel Rodriguez · Julius von Kügelgen · Lars Lorch · Nicolas Donati · Lukas Burkhalter · Xiao Fu · Zhongdao Wang · Songtao Feng · Ciarán Gilligan-Lee · Rishabh Mehrotra · Fangcheng Fu · Jing Yang · Bernhard Schölkopf · Ya-Li Li · Christian Knoll · Maks Ovsjanikov · Andreas Krause · Shengjin Wang · Hong Zhang · Mounia Lalmas · Bolin Ding · Bo Du · Yingbin Liang · Franz Pernkopf · Robert Peharz · Anwar Hithnawi · Julius von Kügelgen · Bo Li · Ce Zhang -
2022 Spotlight: Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks »
Indradyumna Roy · Soumen Chakrabarti · Abir De -
2022 Spotlight: Counterfactual Temporal Point Processes »
Kimia Noorbakhsh · Manuel Rodriguez -
2022 Spotlight: Learning Recourse on Instance Environment to Enhance Prediction Accuracy »
Lokesh N · Guntakanti Sai Koushik · Abir De · Sunita Sarawagi -
2022 Poster: Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection »
Abir De · Soumen Chakrabarti -
2022 Poster: Learning Recourse on Instance Environment to Enhance Prediction Accuracy »
Lokesh N · Guntakanti Sai Koushik · Abir De · Sunita Sarawagi -
2022 Poster: Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks »
Indradyumna Roy · Soumen Chakrabarti · Abir De -
2021 Workshop: Human Centered AI »
Michael Muller · Plamen P Angelov · Shion Guha · Marina Kogan · Gina Neff · Nuria Oliver · Manuel Rodriguez · Adrian Weller -
2021 Poster: Learning to Select Exogenous Events for Marked Temporal Point Process »
Ping Zhang · Rishabh Iyer · Ashish Tendulkar · Gaurav Aggarwal · Abir De -
2021 Poster: Differentiable Learning Under Triage »
Nastaran Okati · Abir De · Manuel Rodriguez -
2021 Poster: Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time »
Anshul Nasery · Soumyadeep Thakur · Vihari Piratla · Abir De · Sunita Sarawagi -
2020 Poster: Decisions, Counterfactual Explanations and Strategic Behavior »
Stratis Tsirtsis · Manuel Gomez Rodriguez -
2019 : Poster Session »
Ayse Cakmak · Yunkai Zhang · Srijith Prabhakarannair Kusumam · Mohamed Osama Ahmed · Xintao Wu · Jayesh Choudhari · David I Inouye · Thomas Taylor · Michel Besserve · Ali Caner Turkmen · Kazi Islam · Antonio Artés · Amrith Setlur · Zhanghua Fu · Zhen Han · Abir De · Nan Du · Pablo Sanchez-Martin -
2019 Workshop: Learning with Temporal Point Processes »
Manuel Rodriguez · Le Song · Isabel Valera · Yan Liu · Abir De · Hongyuan Zha -
2019 Workshop: Workshop on Human-Centric Machine Learning »
Plamen P Angelov · Nuria Oliver · Adrian Weller · Manuel Rodriguez · Isabel Valera · Silvia Chiappa · Hoda Heidari · Niki Kilbertus -
2018 : Manuel Gomez Rodriguez - Enhancing the Accuracy and Fairness of Human Decision Making »
Manuel Rodriguez -
2018 Poster: Deep Reinforcement Learning of Marked Temporal Point Processes »
Utkarsh Upadhyay · Abir De · Manuel Gomez Rodriguez -
2017 Poster: From Parity to Preference-based Notions of Fairness in Classification »
Muhammad Bilal Zafar · Isabel Valera · Manuel Rodriguez · Krishna Gummadi · Adrian Weller -
2016 Poster: Learning and Forecasting Opinion Dynamics in Social Networks »
Abir De · Isabel Valera · Niloy Ganguly · Sourangshu Bhattacharya · Manuel Gomez Rodriguez -
2015 Poster: COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution »
Mehrdad Farajtabar · Yichen Wang · Manuel Rodriguez · Shuang Li · Hongyuan Zha · Le Song -
2015 Oral: COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution »
Mehrdad Farajtabar · Yichen Wang · Manuel Rodriguez · Shuang Li · Hongyuan Zha · Le Song